Initial commit: Ten31 Signal Engine (ingest, scoring brain, corpus seeds)

signal_engine/signals/windows.py

@@ -0,0 +1,53 @@
+"""Temporal windows + windowed independence (the single temporal layer, §4.4).
+
+28-day non-overlapping windows anchored at as_of (W0 ends at as_of, then back). Non-overlapping
+avoids autocorrelation faking significance. The signal is the discrete 2nd derivative of the
+INDEPENDENCE-WEIGHTED flow (EISC per window), never the raw count — so a topic that "accelerates"
+only because one show booked the same guest three times has flat N(W).
+"""
+from __future__ import annotations
+
+from datetime import datetime, timedelta
+
+from .independence import eisc_for
+
+WINDOW_DAYS = 28
+N_WINDOWS = 3
+
+
+def _d(s: str) -> datetime:
+    return datetime.strptime(s[:10], "%Y-%m-%d")
+
+
+def window_bounds(as_of: str, *, n: int = N_WINDOWS, days: int = WINDOW_DAYS) -> list[tuple[int, str, str]]:
+    """Returns [(idx, start_iso, end_iso)] with W0 ending at as_of, extending backward only."""
+    end = _d(as_of)
+    out = []
+    for idx in range(n):
+        w_end = end - timedelta(days=idx * days)
+        w_start = end - timedelta(days=(idx + 1) * days)
+        out.append((idx, w_start.strftime("%Y-%m-%d"), w_end.strftime("%Y-%m-%d")))
+    return out
+
+
+def windowed_independence(conn, rows: list[tuple], as_of: str, *, n: int = N_WINDOWS,
+                          days: int = WINDOW_DAYS) -> dict:
+    """rows: [(date_iso, source_id)]. For each window compute raw count + EISC_adj of its sources.
+    Returns {counts:[c0..], eisc:[N0..], k_eff:[...], acceleration, eisc0, sources0}.
+    acceleration = N0 - 2*N1 + N2 (independence-weighted 2nd derivative)."""
+    bounds = window_bounds(as_of, n=n, days=days)
+    counts, eiscs, keffs, src_sets = [], [], [], []
+    for _idx, start, end in bounds:
+        win = [r for r in rows if r[0] and start < r[0][:10] <= end]
+        srcs = list({r[1] for r in win})
+        e = eisc_for(conn, srcs) if srcs else {"eisc_adj": 0.0, "k_eff": 0}
+        counts.append(len(win))
+        eiscs.append(e["eisc_adj"])
+        keffs.append(e["k_eff"])
+        src_sets.append(srcs)
+    accel = eiscs[0] - 2 * eiscs[1] + eiscs[2] if n >= 3 else 0.0
+    return {
+        "counts": counts, "eisc": [round(x, 3) for x in eiscs], "k_eff": keffs,
+        "acceleration": round(accel, 3), "eisc0": round(eiscs[0], 3), "k_eff0": keffs[0],
+        "sources0": src_sets[0], "n_total": sum(counts),
+    }